Digital Image Reflection Artifact Repair Using Multi-Exposure Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unwanted reflection artifacts, such as 'green ghosts', often appear in digital images captured by integrated computing devices due to optical constraints, rapidly changing positions, and are challenging to detect and repair efficiently.
Innovation Solution
Capture images at different exposure levels to enhance detection of light sources causing reflection artifacts, using machine learning algorithms to track and repair these artifacts by modifying pixel values based on estimated locations and characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If images are captured at normal exposure levels, then the overall image quality is maintained, but unwanted reflection artifacts (green ghosts) cannot be effectively detected
Solution Approach 1:
The system captures an underexposed image before final image processing to identify light source locations. This preliminary detection step allows the system to anticipate and mitigate reflection artifacts in the normally-exposed image, resolving the contradiction by performing detection action in advance with specialized exposure settings.
Solution Approach 2:
The system changes the exposure parameter by capturing images at different exposure levels (underexposed vs. normal). The underexposed images reveal light sources that would be saturated in normal exposure, enabling precise detection of reflection sources without the harmful saturation effect, thus resolving the detection precision contradiction.
2Measurement precision
If multiple images at different exposure levels are captured, then detection accuracy of light sources improves, but processing time and complexity increase
Solution Approach 1:
The processing system segments the image stream into underexposed images (for light source detection) and normally-exposed images (for final output). This segmentation allows parallel processing where underexposed images are analyzed specifically for light source locations, while normally-exposed images are prepared for display, reducing overall processing time despite multiple exposures.
Solution Approach 2:
The system extracts only the critical information (light source locations and characteristics) from the underexposed images, rather than processing the entire image data. This extraction approach minimizes computational overhead while maintaining high detection accuracy, resolving the time complexity contradiction.
3Manufacturing precision
If machine learning algorithms are used to detect and repair artifacts, then repair precision improves, but computational power requirements increase
Solution Approach 1:
Machine learning models are trained in advance on datasets containing light source patterns and reflection artifacts. During actual image processing, the pre-trained models quickly infer light source locations and predict artifact positions, reducing real-time computational requirements while maintaining high repair precision.
Solution Approach 2:
The system uses the underexposed image as a template or copy that contains clear light source information. This template is overlaid or combined with the normally-exposed image to guide the repair process, allowing the machine learning algorithm to work with simplified data structures rather than full-resolution image processing, thus reducing power consumption.
Data Source
AI summary
Devices, methods, and non-transitory computer readable media are disclosed herein to repair or mitigate the appearance of unwanted reflection artifacts in captured video image streams. These unwanted reflection artifacts often present themselves as brightly-colored spots that reflect the shape of a bright light source in the captured image. These artifacts, also referred to herein as “green ghosts” (due to often having a greenish tint), are typically located in regions of the captured images where there is not actually a bright light source located in the image. In fact, such unwanted reflection artifacts often present themselves on the image sensor across the principal point of the lens from where the actual bright light source in the captured image is located. Such devices, methods and computer readable media may be configured to detect, track, and repair such unwanted reflection artifacts in an intelligent fashion, e.g., leveraging images captured with varying exposure settings.